[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PZRWSTT4BKAMD645QQCHNX":3,"skill-same:01M6PZRWSTT4BKAMD645QQCHNX":76},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":27,"publishedAt":48,"linkOnly":49,"markdownContent":50,"markdownBody":51,"frontMatter":52,"refName":36,"commitSha":57,"skillDirectory":58,"forksCount":13,"repositoryHtmlUrl":59,"repositoryHomepageUrl":6,"ownerHtmlUrl":60,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":61,"install":62,"resources":75},"01M6PZRWSTT4BKAMD645QQCHNX","ui-score",null,"Score a UI file's design quality 0-100 against StyleSeed's design language — per-category breakdown, the worst offenders, and a prioritized fix list. A quantified version of \u002Fss-review.","duc-duy-1612\u002FOnline-Delivery-Systems-Web","duc-duy-1612","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F192231384?v=4","01M6NSDKQQDKVTHZ8DZMZ1VYY6","01M6NSDKW8DDVTQHBT1HBDDJPT",0,"MIT","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fui-score\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"ui score","ui","version","blob","design language","tree","ss","critical","main","community","styleseed","design","fix","quality","engine","file","https","license","github","review","2026-11-10 10:12:30",false,"---\nname: ui-score\ndescription: Score a UI file's design quality 0-100 against StyleSeed's design language — per-category breakdown, the worst offenders, and a prioritized fix list. A quantified version of \u002Fss-review.\nrisk: critical\nsource: https:\u002F\u002Fgithub.com\u002Fbitjaru\u002Fstyleseed\u002Ftree\u002Fmain\u002Fengine\u002F.claude\u002Fskills\u002Fss-score\nsource_repo: bitjaru\u002Fstyleseed\nsource_type: community\ndate_added: 2026-07-01\nlicense: MIT\nlicense_source: https:\u002F\u002Fgithub.com\u002Fbitjaru\u002Fstyleseed\u002Fblob\u002Fmain\u002FLICENSE\n---\n\n# Design Score\n## When to Use\n\nUse this skill when you need score a UI file's design quality 0-100 against StyleSeed's design language — per-category breakdown, the worst offenders, and a prioritized fix list. A quantified version of \u002Fss-review.\n\n\n`\u002Fss-review` tells you *what's wrong*. `\u002Fss-score` tells you *how good it is\noverall* and *what to fix first* — a single number plus a category breakdown, so\nyou can track UI quality like you track test coverage.\n\n## When NOT to use\n\n- For a quick pass\u002Ffail before committing → use `\u002Fss-lint`\n- For a full prose audit with fixes → use `\u002Fss-review`\n- For non-UI files (logic, config) — scoring is meaningless\n\n## What to score\n\nScore the file (or each file in a directory) on **six weighted categories** that\nmap to the design language. Total = 100.\n\n| Category | Weight | Reads from |\n|---|---|---|\n| **Color discipline** | 18 | DESIGN-LANGUAGE §1, §18, §72 + VISUAL-CRAFT §C4 |\n| **Hierarchy & typography** | 18 | §2, §3, §4, §16 + Font Size table + VISUAL-CRAFT §C2 |\n| **Layout & rhythm** | 14 | §13, §14, §15, §61 + VISUAL-CRAFT §C1 |\n| **Cards & elevation** | 12 | §7, §8, §12, §1 + VISUAL-CRAFT §C3 |\n| **States & a11y** | 18 | §11, §70, §71, §72 + VISUAL-CRAFT §C3 |\n| **Motion & interaction** | 8 | §24, §59 + `engine\u002Fmotion` |\n| **Coherence** | 12 | VISUAL-CRAFT §C0 (one choice per axis) |\n\n## How to score each category\n\nFor each category, start at full marks and **subtract** for violations you find by\nreading the code. Be specific and evidence-based — cite the line.\n\n**Color discipline (20)** — deduct for: any `#000`\u002F`text-black` (−4 each, cap −8);\nmore than one accent hue used decoratively (−5); **emoji used as UI icons** (multi-color,\nbreaks single accent) (−5); **a normal\u002FOK\u002F\"보통\" state shown in a status color** instead of\nneutral grey (−4); **status color on most\u002Fevery row** (no severity hierarchy) (−4);\n**decorative hues** (gold stars, rainbow category dots) instead of accent\u002Fgrey (−3);\nhardcoded hex where a semantic token exists (−2 each, cap −6); status conveyed by color\nalone (−4).\n\n**Hierarchy & typography (20)** — deduct for: number\u002Funit not ~2:1 (−4); font\nsizes off the Font Size table \u002F `text-[var(--…)]` for size (−5); everything the\nsame weight, no clear primary (−5); cramped or wrong line-height on body (−3).\n\n**Layout & rhythm (15)** — deduct for: content on bare background, not in cards\n(−6); `px-4`\u002F`px-8`\u002F`mx-4` instead of `px-6`\u002F`mx-6` (−3); same section type\nrepeated in a row (−4); no `space-y-6` rhythm (−3).\n\n**Cards & elevation (15)** — deduct for: 1px borders doing separation work that\ntone+shadow should (−4); shadows over ~8% opacity \u002F visibly heavy (−4); no\ncard\u002Fbackground tone separation (−5).\n\n**States & a11y (20)** — deduct for: missing empty\u002Floading\u002Ferror state on a data\nsurface (−5 each, cap −10); contrast below 4.5:1 body \u002F 3:1 large (−6); touch\ntarget \u003C 44px (−4); no visible focus \u002F `outline:none` (−5); icon-only control\nwithout `aria-label` (−3).\n\n**Motion & interaction (8)** — deduct for: random\u002Fad-hoc fades instead of a named\nseed\u002Fkeyword (−3); motion that delays content or blocks an action (−4); no\n`prefers-reduced-motion` handling on custom motion (−3); scroll-linked\u002Fparallax\n(forbidden, §59) (−5).\n\n**Coherence (12)** — the \"one choice per axis\" laws (VISUAL-CRAFT §C0). Deduct for\neach axis that is *mixed* rather than unified across the file: mixed radius\npersonalities, e.g. sharp panel + pill buttons (−5); two+ competing accent hues used\nfor emphasis (−4); mixed shadow languages \u002F light directions (−3); mixed icon\nfamilies, fill modes, or stroke weights (−3); same radius on a nested element instead\nof `inner = outer − padding` (−2); inconsistent control heights for buttons\u002Finputs\n(−2). This is the category that most predicts \"looks AI-generated\" — weight evidence\nof system-wide consistency, not per-component prettiness.\n\nClamp each category at 0. Sum to a total.\n\n## Output format\n\n```\n## Design Score: 70 \u002F 100   (src\u002Fapp\u002FDashboard.tsx)\n\n████████████████░░░░░░  C-\n\nColor discipline      13\u002F18   ▓▓▓░  #000 headings (l.12,40); orange+blue+green accents (l.28-34)\nHierarchy & typography 15\u002F18  ▓▓▓▓  number\u002Funit 1:1 on hero (l.18)\nLayout & rhythm        11\u002F14  ▓▓▓░  two identical KPI rows (l.22-31)\nCards & elevation       8\u002F12  ▓▓░░  1px borders doing separation (l.22)\nStates & a11y          11\u002F18  ▓▓░░  no empty\u002Floading state; focus ring missing (l.55)\nMotion & interaction    6\u002F8   ▓▓▓░  default fade, not a named seed\nCoherence               6\u002F12  ▓▓░░  sharp cards (l.22) + pill buttons (l.48); 3 accent hues (§C0)\n\n### Fix first (highest score gain)\n1. Add empty + loading states to the orders list       → +7 states (§71)\n2. Unify radius (pick soft 8-12px) + collapse to one accent → +9 coherence+color (§C0, §2)\n3. Drop the 1px borders, use tone + ≤8% shadow         → +4 cards  (§7)\n\nRe-score after: ~92 \u002F 100.\n```\n\nUse letter bands: 90+ A · 80-89 B · 70-79 C · 60-69 D · \u003C60 F.\n\n## Gate mode (use this as the Quality Gate before showing the user UI)\n\nThe Quality Gate (CLAUDE.md \u002F AGENTS.md) is `\u002Fss-score` run as a loop, not a one-off:\n\n1. Score the just-generated UI.\n2. If **\u003C 80**, apply the \"fix first\" list (use `\u002Fss-review` to make the edits), then **re-score**.\n3. Repeat up to ~3×, or until ≥ 80.\n4. Present the UI with the final score and a one-line \"fixed: …\".\n\nThe pass bar is a **floor, not a ceiling** — get to ≥ 80 and stop; don't chase 100. The point\nis that no first-draft, obviously-incoherent UI reaches the user. Especially never ship below\n80 with a rainbow status list, emoji icons, two accents, or missing states — those are the\nexact tells the gate exists to catch.\n\n## Rules\n\n- **Read the file** — score from real evidence (line numbers), never guess.\n- Order the \"fix first\" list by **score gain**, not by severity alone — the goal\n  is the fastest path to a better number.\n- For a directory, print a one-line score per file, then the lowest-scoring file's\n  full breakdown.\n- Don't auto-edit in plain scoring. `\u002Fss-score` measures; `\u002Fss-review` and `\u002Fss-motion` fix.\n  In **Gate mode** (above) you do fix-and-re-score until the floor is met.\n- As a *gate*, ≥ 80 is a floor before showing the user — but don't over-polish: chasing 95→100\n  to delay shipping is worse than shipping a clean 85.\n\n## Limitations\n\n- Use this skill only when the task clearly matches its upstream source and local project context.\n- Verify commands, generated code, dependencies, credentials, and external service behavior before applying changes.\n- Do not treat examples as a substitute for environment-specific tests, security review, or user approval for destructive or costly actions.\n","# Design Score\n## When to Use\n\nUse this skill when you need score a UI file's design quality 0-100 against StyleSeed's design language — per-category breakdown, the worst offenders, and a prioritized fix list. A quantified version of \u002Fss-review.\n\n\n`\u002Fss-review` tells you *what's wrong*. `\u002Fss-score` tells you *how good it is\noverall* and *what to fix first* — a single number plus a category breakdown, so\nyou can track UI quality like you track test coverage.\n\n## When NOT to use\n\n- For a quick pass\u002Ffail before committing → use `\u002Fss-lint`\n- For a full prose audit with fixes → use `\u002Fss-review`\n- For non-UI files (logic, config) — scoring is meaningless\n\n## What to score\n\nScore the file (or each file in a directory) on **six weighted categories** that\nmap to the design language. Total = 100.\n\n| Category | Weight | Reads from |\n|---|---|---|\n| **Color discipline** | 18 | DESIGN-LANGUAGE §1, §18, §72 + VISUAL-CRAFT §C4 |\n| **Hierarchy & typography** | 18 | §2, §3, §4, §16 + Font Size table + VISUAL-CRAFT §C2 |\n| **Layout & rhythm** | 14 | §13, §14, §15, §61 + VISUAL-CRAFT §C1 |\n| **Cards & elevation** | 12 | §7, §8, §12, §1 + VISUAL-CRAFT §C3 |\n| **States & a11y** | 18 | §11, §70, §71, §72 + VISUAL-CRAFT §C3 |\n| **Motion & interaction** | 8 | §24, §59 + `engine\u002Fmotion` |\n| **Coherence** | 12 | VISUAL-CRAFT §C0 (one choice per axis) |\n\n## How to score each category\n\nFor each category, start at full marks and **subtract** for violations you find by\nreading the code. Be specific and evidence-based — cite the line.\n\n**Color discipline (20)** — deduct for: any `#000`\u002F`text-black` (−4 each, cap −8);\nmore than one accent hue used decoratively (−5); **emoji used as UI icons** (multi-color,\nbreaks single accent) (−5); **a normal\u002FOK\u002F\"보통\" state shown in a status color** instead of\nneutral grey (−4); **status color on most\u002Fevery row** (no severity hierarchy) (−4);\n**decorative hues** (gold stars, rainbow category dots) instead of accent\u002Fgrey (−3);\nhardcoded hex where a semantic token exists (−2 each, cap −6); status conveyed by color\nalone (−4).\n\n**Hierarchy & typography (20)** — deduct for: number\u002Funit not ~2:1 (−4); font\nsizes off the Font Size table \u002F `text-[var(--…)]` for size (−5); everything the\nsame weight, no clear primary (−5); cramped or wrong line-height on body (−3).\n\n**Layout & rhythm (15)** — deduct for: content on bare background, not in cards\n(−6); `px-4`\u002F`px-8`\u002F`mx-4` instead of `px-6`\u002F`mx-6` (−3); same section type\nrepeated in a row (−4); no `space-y-6` rhythm (−3).\n\n**Cards & elevation (15)** — deduct for: 1px borders doing separation work that\ntone+shadow should (−4); shadows over ~8% opacity \u002F visibly heavy (−4); no\ncard\u002Fbackground tone separation (−5).\n\n**States & a11y (20)** — deduct for: missing empty\u002Floading\u002Ferror state on a data\nsurface (−5 each, cap −10); contrast below 4.5:1 body \u002F 3:1 large (−6); touch\ntarget \u003C 44px (−4); no visible focus \u002F `outline:none` (−5); icon-only control\nwithout `aria-label` (−3).\n\n**Motion & interaction (8)** — deduct for: random\u002Fad-hoc fades instead of a named\nseed\u002Fkeyword (−3); motion that delays content or blocks an action (−4); no\n`prefers-reduced-motion` handling on custom motion (−3); scroll-linked\u002Fparallax\n(forbidden, §59) (−5).\n\n**Coherence (12)** — the \"one choice per axis\" laws (VISUAL-CRAFT §C0). Deduct for\neach axis that is *mixed* rather than unified across the file: mixed radius\npersonalities, e.g. sharp panel + pill buttons (−5); two+ competing accent hues used\nfor emphasis (−4); mixed shadow languages \u002F light directions (−3); mixed icon\nfamilies, fill modes, or stroke weights (−3); same radius on a nested element instead\nof `inner = outer − padding` (−2); inconsistent control heights for buttons\u002Finputs\n(−2). This is the category that most predicts \"looks AI-generated\" — weight evidence\nof system-wide consistency, not per-component prettiness.\n\nClamp each category at 0. Sum to a total.\n\n## Output format\n\n```\n## Design Score: 70 \u002F 100   (src\u002Fapp\u002FDashboard.tsx)\n\n████████████████░░░░░░  C-\n\nColor discipline      13\u002F18   ▓▓▓░  #000 headings (l.12,40); orange+blue+green accents (l.28-34)\nHierarchy & typography 15\u002F18  ▓▓▓▓  number\u002Funit 1:1 on hero (l.18)\nLayout & rhythm        11\u002F14  ▓▓▓░  two identical KPI rows (l.22-31)\nCards & elevation       8\u002F12  ▓▓░░  1px borders doing separation (l.22)\nStates & a11y          11\u002F18  ▓▓░░  no empty\u002Floading state; focus ring missing (l.55)\nMotion & interaction    6\u002F8   ▓▓▓░  default fade, not a named seed\nCoherence               6\u002F12  ▓▓░░  sharp cards (l.22) + pill buttons (l.48); 3 accent hues (§C0)\n\n### Fix first (highest score gain)\n1. Add empty + loading states to the orders list       → +7 states (§71)\n2. Unify radius (pick soft 8-12px) + collapse to one accent → +9 coherence+color (§C0, §2)\n3. Drop the 1px borders, use tone + ≤8% shadow         → +4 cards  (§7)\n\nRe-score after: ~92 \u002F 100.\n```\n\nUse letter bands: 90+ A · 80-89 B · 70-79 C · 60-69 D · \u003C60 F.\n\n## Gate mode (use this as the Quality Gate before showing the user UI)\n\nThe Quality Gate (CLAUDE.md \u002F AGENTS.md) is `\u002Fss-score` run as a loop, not a one-off:\n\n1. Score the just-generated UI.\n2. If **\u003C 80**, apply the \"fix first\" list (use `\u002Fss-review` to make the edits), then **re-score**.\n3. Repeat up to ~3×, or until ≥ 80.\n4. Present the UI with the final score and a one-line \"fixed: …\".\n\nThe pass bar is a **floor, not a ceiling** — get to ≥ 80 and stop; don't chase 100. The point\nis that no first-draft, obviously-incoherent UI reaches the user. Especially never ship below\n80 with a rainbow status list, emoji icons, two accents, or missing states — those are the\nexact tells the gate exists to catch.\n\n## Rules\n\n- **Read the file** — score from real evidence (line numbers), never guess.\n- Order the \"fix first\" list by **score gain**, not by severity alone — the goal\n  is the fastest path to a better number.\n- For a directory, print a one-line score per file, then the lowest-scoring file's\n  full breakdown.\n- Don't auto-edit in plain scoring. `\u002Fss-score` measures; `\u002Fss-review` and `\u002Fss-motion` fix.\n  In **Gate mode** (above) you do fix-and-re-score until the floor is met.\n- As a *gate*, ≥ 80 is a floor before showing the user — but don't over-polish: chasing 95→100\n  to delay shipping is worse than shipping a clean 85.\n\n## Limitations\n\n- Use this skill only when the task clearly matches its upstream source and local project context.\n- Verify commands, generated code, dependencies, credentials, and external service behavior before applying changes.\n- Do not treat examples as a substitute for environment-specific tests, security review, or user approval for destructive or costly actions.\n",{"name":5,"risk":35,"source":53,"license":14,"date_added":54,"description":7,"source_repo":55,"source_type":37,"license_source":56},"https:\u002F\u002Fgithub.com\u002Fbitjaru\u002Fstyleseed\u002Ftree\u002Fmain\u002Fengine\u002F.claude\u002Fskills\u002Fss-score",1782864000000,"bitjaru\u002Fstyleseed","https:\u002F\u002Fgithub.com\u002Fbitjaru\u002Fstyleseed\u002Fblob\u002Fmain\u002FLICENSE","f3312ba749561b6159f477dbfc9313c875d40a56",".agents\u002Fskills_archive\u002Fui-score","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612","2026-10-25 23:50:58",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill ui-score",{"tool":68,"command":69},"bunx","bunx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill ui-score",{"tool":71,"command":72},"pnpm","pnpm dlx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill ui-score","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fui-score\u002FSKILL.md",true,[],[77,103,126,147,173,197],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":86,"publishedAt":48},"01M6Q0FA5FZ410Z33Z3TFQ4DBA","zero-trust","Implement zero-trust network architecture. Configure identity-based access, micro-segmentation, and continuous verification. Use when implementing modern security architectures.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzero-trust\u002FSKILL.md",[83],{"categoryNo":84,"categoryName":85,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[87,88,89,90,91,92,79,93,94,95,96,97,37,36,98,35,99,100,101,102],"ZeRO","trust","zero trust","architecture","assessment","verification","segmentation","devops-security","access","configure","only","active","scope","scripts","relevant","implementing",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":48},"01M6Q0F1YZJW3KX5FBKEVZ8CV4","zcode-delegate","Delegate coding tasks to the Z.AI ZCode CLI only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzcode-delegate\u002FSKILL.md",[],[110,111,112,47,113,114,115,116,117,118,119,120,121,97,122,37,123,124,35,125],"delegate","zcode","zcode delegate","cli","orchestration","tasks","run","Bash","model","node","read","orchestrator","files","desktop app","app","agent-orchestration",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":48},"01M6Q0ETK41VGNMYEXW0T00AJN","youtube-transcript","Fetch YouTube transcripts through DeepAPI or local fallback tooling and save clean text output.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript\u002FSKILL.md",[],[133,134,135,136,46,137,138,45,44,139,140,141,142,37,36,143,144,145,146,31],"transcript","youtube transcript","youtube","safe","codex","research","text","fetch","tooling","clean","local","output","deepapi","youtube transcripts",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":162,"publishedAt":48},"01M6Q0EPPH2PVMDW40017F8WX0","youtube-transcript-skills","Fetch YouTube video transcripts, search videos\u002Fchannels, browse channels, and extract playlists via the getyoutubetranscript.com API - free tier, no card required.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript-skills\u002FSKILL.md",[153,156,159],{"categoryNo":154,"categoryName":155,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":157,"categoryName":158,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":160,"categoryName":161,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000030","开发工程师",[133,134,135,163,136,164,46,137,45,165,166,167,168,140,169,37,36,170,171,172],"youtube transcript skills","gemini","search","api","Video","browse","api-integration","free","card","channels",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":183,"publishedAt":48},"01M6Q0EAB96PX83W5PTE8A0R8D","youtube-notetaker","Turn YouTube talks into local study notes with slides, transcripts, editable annotations, and a markdown-backed viewer.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002FSKILL.md",[179,182],{"categoryNo":180,"categoryName":181,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":157,"categoryName":158,"taxonomyType":20,"taxonomyTypeDesc":21},[135,184,185,113,136,186,187,188,189,45,167,190,191,192,193,36,194,143,195,196],"youtube notetaker","notetaker","workflow","official","notes","code","markdown","slides","annotations","README","study","dair-academy","viewer",{"skillNo":198,"name":199,"nameZh":6,"description":200,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":201,"categories":202,"keywords":204,"publishedAt":48},"01M6Q0E55F0GW5MX48V8HXS8B5","youtube-full","Fetch YouTube transcripts, search videos, browse channels, and extract playlists via TranscriptAPI — no yt-dlp, no Google API key, works from any cloud server.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-full\u002FSKILL.md",[203],{"categoryNo":154,"categoryName":155,"taxonomyType":20,"taxonomyTypeDesc":21},[205,135,206,207,136,164,165,208,209,166,167,168,140,210,169,37,36,170,211,146],"youtube full","full","google","server","dlp","credits","automatic"]